Robust Mitosis Detection Using a Cascade Mask-RCNN Approach With Domain-Specific Residual Cycle-GAN Data Augmentation
This work addresses the problem of robust mitosis detection for medical diagnosis, but it is incremental as it builds on existing methods like Mask-RCNN and Cycle-GAN with domain-specific adaptations.
The paper tackled mitosis detection in histopathology images by developing a cascade algorithm with Mask-RCNN and a classification ensemble, enhanced by domain-specific data augmentation using a residual Cycle-GAN, achieving an F1 score of 0.7578 and second place in the MIDOG challenge.
For the MIDOG mitosis detection challenge, we created a cascade algorithm consisting of a Mask-RCNN detector, followed by a classification ensemble consisting of ResNet50 and DenseNet201 to refine detected mitotic candidates. The MIDOG training data consists of 200 frames originating from four scanners, three of which are annotated for mitotic instances with centroid annotations. Our main algorithmic choices are as follows: first, to enhance the generalizability of our detector and classification networks, we use a state-of-the-art residual Cycle-GAN to transform each scanner domain to every other scanner domain. During training, we then randomly load, for each image, one of the four domains. In this way, our networks can learn from the fourth non-annotated scanner domain even if we don't have annotations for it. Second, for training the detector network, rather than using centroid-based fixed-size bounding boxes, we create mitosis-specific bounding boxes. We do this by manually annotating a small selection of mitoses, training a Mask-RCNN on this small dataset, and applying it to the rest of the data to obtain full annotations. We trained the follow-up classification ensemble using only the challenge-provided positive and hard-negative examples. On the preliminary test set, the algorithm scores an F1 score of 0.7578, putting us as the second-place team on the leaderboard.